bigquery: rename name field of Dataset to dataset_id (#3955)

* bigquery: rename name field of Dataset to dataset_id Rename the former dataset_id property to full_dataset_id. Also rename Table.dataset_name to Table.dataset_id. Perform other renamings (of various variables and constants). These names match usage better. The API's Dataset.id field is "project:dataset_id", which is confusing and basically useless, so it's a mistake to call that dataset_id. * fix long line * fix long line

Author: jba

bigquery/google/cloud/bigquery/dataset.py

@@ -142,8 +142,8 @@ class Dataset(object):
  See
  https://cloud.google.com/bigquery/docs/reference/rest/v2/datasets
 
- :type name: str
- :param name: the name of the dataset
+ :type dataset_id: str
+ :param dataset_id: the ID of the dataset
 
  :type client: :class:`google.cloud.bigquery.client.Client`
  :param client: A client which holds credentials and project configuration
@@ -159,8 +159,8 @@ class Dataset(object):
 
  _access_entries = None
 
- def __init__(self, name, client, access_entries=(), project=None):
- self.name = name
+ def __init__(self, dataset_id, client, access_entries=(), project=None):
+ self.dataset_id = dataset_id
  self._client = client
  self._properties = {}
  # Let the @property do validation.
@@ -181,9 +181,9 @@ def path(self):
  """URL path for the dataset's APIs.
 
  :rtype: str
- :returns: the path based on project and dataste name.
+ :returns: the path based on project and dataset ID.
  """
- return '/projects/%s/datasets/%s' % (self.project, self.name)
+ return '/projects/%s/datasets/%s' % (self.project, self.dataset_id)
 
  @property
  def access_entries(self):
@@ -221,8 +221,8 @@ def created(self):
  return _datetime_from_microseconds(1000.0 * creation_time)
 
  @property
- def dataset_id(self):
- """ID for the dataset resource.
+ def full_dataset_id(self):
+ """ID for the dataset resource, in the form "project_id:dataset_id".
 
  :rtype: str, or ``NoneType``
  :returns: the ID (None until set from the server).
@@ -365,8 +365,8 @@ def from_api_repr(cls, resource, client):
  'datasetId' not in resource['datasetReference']):
  raise KeyError('Resource lacks required identity information:'
  '["datasetReference"]["datasetId"]')
- name = resource['datasetReference']['datasetId']
- dataset = cls(name, client=client)
+ dataset_id = resource['datasetReference']['datasetId']
+ dataset = cls(dataset_id, client=client)
  dataset._set_properties(resource)
  return dataset
 
@@ -444,7 +444,7 @@ def _build_resource(self):
  """Generate a resource for ``create`` or ``update``."""
  resource = {
  'datasetReference': {
- 'projectId': self.project, 'datasetId': self.name},
+ 'projectId': self.project, 'datasetId': self.dataset_id},
  }
  if self.default_table_expiration_ms is not None:
  value = self.default_table_expiration_ms
@@ -610,7 +610,8 @@ def list_tables(self, max_results=None, page_token=None):
  :returns: Iterator of :class:`~google.cloud.bigquery.table.Table`
  contained within the current dataset.
  """
- path = '/projects/%s/datasets/%s/tables' % (self.project, self.name)
+ path = '/projects/%s/datasets/%s/tables' % (
+ self.project, self.dataset_id)
  result = page_iterator.HTTPIterator(
  client=self._client,
  api_request=self._client._connection.api_request,

bigquery/google/cloud/bigquery/job.py

@@ -773,7 +773,7 @@ def _build_resource(self):
  'sourceUris': self.source_uris,
  'destinationTable': {
  'projectId': self.destination.project,
- 'datasetId': self.destination.dataset_name,
+ 'datasetId': self.destination.dataset_id,
  'tableId': self.destination.name,
  },
  },
@@ -900,7 +900,7 @@ def _build_resource(self):
 
  source_refs = [{
  'projectId': table.project,
- 'datasetId': table.dataset_name,
+ 'datasetId': table.dataset_id,
  'tableId': table.name,
  } for table in self.sources]
 
@@ -914,7 +914,7 @@ def _build_resource(self):
  'sourceTables': source_refs,
  'destinationTable': {
  'projectId': self.destination.project,
- 'datasetId': self.destination.dataset_name,
+ 'datasetId': self.destination.dataset_id,
  'tableId': self.destination.name,
  },
  },
@@ -1058,7 +1058,7 @@ def _build_resource(self):
 
  source_ref = {
  'projectId': self.source.project,
- 'datasetId': self.source.dataset_name,
+ 'datasetId': self.source.dataset_id,
  'tableId': self.source.name,
  }
 
@@ -1247,7 +1247,7 @@ def _destination_table_resource(self):
  if self.destination is not None:
  return {
  'projectId': self.destination.project,
- 'datasetId': self.destination.dataset_name,
+ 'datasetId': self.destination.dataset_id,
  'tableId': self.destination.name,
  }
 
@@ -1271,7 +1271,7 @@ def _populate_config_resource(self, configuration):
  if self.default_dataset is not None:
  configuration['defaultDataset'] = {
  'projectId': self.default_dataset.project,
- 'datasetId': self.default_dataset.name,
+ 'datasetId': self.default_dataset.dataset_id,
  }
  if self.destination is not None:
  table_res = self._destination_table_resource()

bigquery/google/cloud/bigquery/query.py

@@ -329,7 +329,7 @@ def _build_resource(self):
  if self.default_dataset is not None:
  resource['defaultDataset'] = {
  'projectId': self.project,
- 'datasetId': self.default_dataset.name,
+ 'datasetId': self.default_dataset.dataset_id,
  }
 
  if self.max_results is not None:

bigquery/google/cloud/bigquery/table.py

@@ -119,13 +119,13 @@ def project(self):
  return self._dataset.project
 
  @property
- def dataset_name(self):
- """Name of dataset containing the table.
+ def dataset_id(self):
+ """ID of dataset containing the table.
 
  :rtype: str
  :returns: the ID (derived from the dataset).
  """
- return self._dataset.name
+ return self._dataset.dataset_id
 
  @property
  def path(self):
@@ -463,7 +463,7 @@ def list_partitions(self, client=None):
  """
  query = self._require_client(client).run_sync_query(
  'SELECT partition_id from [%s.%s$__PARTITIONS_SUMMARY__]' %
- (self.dataset_name, self.name))
+ (self.dataset_id, self.name))
  query.run()
  return [row[0] for row in query.rows]
 
@@ -527,7 +527,7 @@ def _build_resource(self):
  resource = {
  'tableReference': {
  'projectId': self._dataset.project,
- 'datasetId': self._dataset.name,
+ 'datasetId': self._dataset.dataset_id,
  'tableId': self.name},
  }
  if self.description is not None:
@@ -572,7 +572,7 @@ def create(self, client=None):
  """
  client = self._require_client(client)
  path = '/projects/%s/datasets/%s/tables' % (
- self._dataset.project, self._dataset.name)
+ self._dataset.project, self._dataset.dataset_id)
  api_response = client._connection.api_request(
  method='POST', path=path, data=self._build_resource())
  self._set_properties(api_response)
@@ -1361,7 +1361,7 @@ def _get_upload_metadata(source_format, schema, dataset, name):
  'sourceFormat': source_format,
  'destinationTable': {
  'projectId': dataset.project,
- 'datasetId': dataset.name,
+ 'datasetId': dataset.dataset_id,
  'tableId': name,
  },
  }